R Notebook

library(dplyr)
library(ggplot2)
library(ggrepel)
library(GOplot)

Loading required package: ggdendro
Loading required package: gridExtra

Attaching package: ‘gridExtra’

The following object is masked from ‘package:dplyr’:

    combine

Loading required package: RColorBrewer

GO bubble plot

circ <- circle_dat(terms, genes)

Error in circle_dat(terms, genes) : could not find function "circle_dat"

terms <- create_terms(gsea)
genes <- create_genes(genelist)
circ <- circle_dat(terms, genes)

GOBubble_modified <- function(data, display, title, colour, labels, ID = T, table.legend = T, table.col = T, bg.col = F, zscore_threshold=0, ggrepel_linecol='black', text_size_axes=20, text_size_axes_label=20, text_size=10, text_size_legend=7, text_size_threshold=10, legend_point_size=20){
  zscore <- adj_pval <- category <- count <- id <- term <- NULL
  if (missing(display)) display <- 'single'
  if (missing(title)) title <- ''
  if (missing(colour)) cols <- c("chartreuse4", "brown2", "cornflowerblue") else cols <- colour
  if (missing(labels)) labels <- 5
  if (bg.col == T & display == 'single') cat("Parameter bg.col will be ignored. To use the parameter change display to 'multiple'")
  
  colnames(data) <- tolower(colnames(data))
  tmp_lab <- data.frame(cats = c('Biological Process', 'Cellular Component', 'Molecular Function'), 
                        cat.abb = c('BP', 'CC', 'MF'),
                        locy = c(match('BP', data$category), match('CC', data$category), match('MF', data$category)),
                        cols = cols,
                        stringsAsFactors = F)
  tmp_lab <- tmp_lab[order(tmp_lab$locy),]
  if(!'count'%in%colnames(data)){
    rang <- c(5, 5)
    data$count <- rep(1, dim(data)[1])
  }else {rang <- c(1, 30)}
  data$adj_pval <- -log(data$adj_pval, 10)
  sub <- data[!duplicated(data$term), ]
  g <- ggplot(sub, aes(zscore, adj_pval, fill = category, size = count))+
    labs(title = title, x = 'z-score', y = '-log (adj p-value)')+
    geom_point(shape = 21, col = 'black', alpha = 1 / 2)+ #add all bubbles
    geom_hline(yintercept = 1.3, col = 'orange')+ #add threshold for p-value=0.05
    scale_size(range = rang, guide = 'none') +
    scale_y_continuous(limits=c(0,45))
  
  sub2 <- subset(sub, subset=sub$adj_pval >= labels)
  sub2 <- subset(sub2, subset=abs(sub2$zscore) >= zscore_threshold)

    g <- g + scale_fill_manual('', values = tmp_lab$cols, labels = tmp_lab$cats)+
      theme(legend.position = 'right', legend.key.size = unit(1, 'cm'), legend.title=element_text(face='bold')) +
      guides(fill = guide_legend(override.aes = list(size=legend_point_size)))
      annotate ("text", x = 0.6, y = 2.2, label = "Threshold", colour = "orange", size = text_size_threshold)
    g <- g + geom_text_repel(data = sub2, aes(x = zscore, y = adj_pval, label = term), size = text_size, segment.color = ggrepel_linecol)
    g <-  g + 
        theme(axis.text = element_text(size = text_size_axes), axis.line = element_line(colour = 'grey80'), axis.ticks = element_line(colour = 'grey80'), axis.title = element_text(size = text_size_axes_label, face = 'bold'), panel.background = element_blank(), panel.grid.minor = element_blank(), panel.grid.major = element_blank(), plot.background = element_blank(), legend.text=element_text(size=text_size_legend), legend.title=element_text(size=text_size_legend))
 return(g)
}